A GIS Based Landslide Susceptibility Mapping Using Multi-Criteria Decision Analysis Model at a Regional Scale

The paper aims to produce a landslide susceptibility map by means of multi-criteria decision analysis based on GIS for Qianyang County, Shaanxi Province, China. At first, a detailed landslide inventory map was prepared and fourteen landside conditioning factors were considered: slope aspect, slope angle, altitude, plan curvature, profile curvature, geomorphology, rainfall, STI, TWI, SPI, distance to faults, distance to rivers, distance to roads, and NDVI. The landslide locations were detected from the interpretation of aerial photographs, and supported by field surveys. A total of 81 landslides identified in the study area were randomly split into two parts: the training dataset 70% (56 landslides) for establishing the model and the remaining 30% (25 landslides) was used for the model validation. The ArcGIS package was used to evaluate landslide susceptibility and analyze landslide conditioning factors, as a result, a landslide susceptibility map was generated through multi-criteria decision analysis based on ArcGIS 10.0 and divided into five susceptibility classes: very low, low, moderate, high, and very high. Finally, in order to validate the accuracy of the landslide susceptibility map, the area under the curve (AUC) was applied. The AUC plot assessment results show that the susceptibility map has a training accuracy of 77.58% and the prediction accuracy of 71.40%.